© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112131
    Prev
    Next
    INDEX
    Explanations

    conditions and requests

    np_acts-logits-general · gemini-2.5-flash-lite

    Moral Injury, Management Roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ي
    0.55
    emu
    0.50
    ems
    0.50
    ews
    0.49
    يت
    0.48
    يح
    0.48
    '
    0.47
    את
    0.47
     emphasized
    0.46
    au
    0.45
    POSITIVE LOGITS
    Leffler
    0.50
     platelet
    0.49
     तलैया
    0.48
     Yoruba
    0.47
    ິກ
    0.46
    श्विक
    0.45
    शियल
    0.45
    ᱨ
    0.44
     brunette
    0.44
     likeness
    0.44
    Activations Density 0.001%

    No Known Activations